paper-with-me

Papers

Provable Gradient Variance Guarantees for Black-Box Variational Inference

2019-06-19 · NeurIPS 2019 12 · Justin Domke

Recent variational inference methods use stochastic gradient estimators whose variance is not well understood. Theoretical guarantees for these estimators are important to understand when these methods will or will not work. This paper gives bounds for the common "reparameterization" estimators when the target is smooth and the variational family is a location-scale distribution. These bounds are unimprovable and thus provide the best possible guarantees under the stated assumptions.

📄 PDF Abstract BibTeX arXiv:1906.08241

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Similar Papers 제목 키워드 기반

Provable Smoothness Guarantees for Black-Box Variational Inference

2019-01-24 · ICML 2020 1 · Justin Domke

Black-box variational inference tries to approximate a complex target distribution though a gradient-based optimization of the parameters of a simpler distribution. Provable convergence guarantees require structural prop…

Variational Inference

Provable convergence guarantees for black-box variational inference

2023-06-04 · NeurIPS 2023 11 · Justin Domke, Guillaume Garrigos, Robert Gower

Black-box variational inference is widely used in situations where there is no proof that its stochastic optimization succeeds. We suggest this is due to a theoretical gap in existing stochastic optimization proofs: name…

Stochastic OptimizationVariational Inference

Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?

2023-07-27 · Kyurae Kim, Yian Ma, Jacob R. Gardner

We prove that black-box variational inference (BBVI) with control variates, particularly the sticking-the-landing (STL) estimator, converges at a geometric (traditionally called "linear") rate under perfect variational f…

Variational Inference

Joint control variate for faster black-box variational inference

2022-10-13 · Xi Wang, Tomas Geffner, Justin Domke

Black-box variational inference performance is sometimes hindered by the use of gradient estimators with high variance. This variance comes from two sources of randomness: Data subsampling and Monte Carlo sampling. While…

Stochastic OptimizationVariational Inference

SGD for Variational Inference: Tackling Unbounded Variance via Preconditioning and Dynamic Batching

2026-05-08 · Hippolyte Labarrière, Cesare Molinari, Silvia Villa, Lorenzo Rosasco arxiv

Black-Box Variational Inference (BBVI) typically relies on Stochastic Gradient Descent (SGD) to optimize the Evidence Lower Bound (ELBO). However, the stochastic gradients in BBVI inherently exhibit unbounded variance, v…

Stochastic Optimization